CN111551947A - Laser point cloud positioning method, device, equipment and system - Google Patents

Laser point cloud positioning method, device, equipment and system Download PDF

Info

Publication number
CN111551947A
CN111551947A CN202010469927.5A CN202010469927A CN111551947A CN 111551947 A CN111551947 A CN 111551947A CN 202010469927 A CN202010469927 A CN 202010469927A CN 111551947 A CN111551947 A CN 111551947A
Authority
CN
China
Prior art keywords
point cloud
laser point
positioning
target
static
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010469927.5A
Other languages
Chinese (zh)
Inventor
于占海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Neusoft Reach Automotive Technology Shenyang Co Ltd
Original Assignee
Neusoft Reach Automotive Technology Shenyang Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Neusoft Reach Automotive Technology Shenyang Co Ltd filed Critical Neusoft Reach Automotive Technology Shenyang Co Ltd
Priority to CN202010469927.5A priority Critical patent/CN111551947A/en
Publication of CN111551947A publication Critical patent/CN111551947A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/481—Constructional features, e.g. arrangements of optical elements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/481—Constructional features, e.g. arrangements of optical elements
    • G01S7/4811—Constructional features, e.g. arrangements of optical elements common to transmitter and receiver
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Electromagnetism (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

The disclosure relates to a laser point cloud positioning method, device, equipment and system, and belongs to the technical field of laser point cloud positioning. The laser point cloud positioning method provided by the disclosure improves positioning accuracy and efficiency. Specifically, the method comprises: acquiring a first laser point cloud through a scanning device; removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud; and positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.

Description

Laser point cloud positioning method, device, equipment and system
Technical Field
The present disclosure relates to the field of laser point cloud positioning technologies, and in particular, to a method, an apparatus, a device, and a system for laser point cloud positioning.
Background
In the field of autonomous driving, autonomous driving systems plan driving solutions for vehicles by accurate positioning. The related art provides a laser point cloud positioning method. Specifically, laser point clouds of the current position are obtained through a scanning device on the vehicle, and then the vehicle is located in a laser point cloud map according to the laser power supply.
However, the laser point cloud positioning method adopted in the related art has the defects of poor positioning accuracy and low positioning efficiency, and has a space for further improvement.
Disclosure of Invention
The present disclosure provides a laser point cloud positioning method, device, apparatus and system to solve the defects in the related art.
In a first aspect, an embodiment of the present disclosure provides a laser point cloud positioning method. The method comprises the following steps:
acquiring a first laser point cloud through a scanning device;
removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud;
and positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
In one embodiment, the removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud includes:
identifying a category of a target object in the first laser point cloud;
determining the dynamic target in the target object according to the category;
and removing the point cloud identifying the dynamic target to obtain the static laser point cloud.
In one embodiment, said determining said dynamic target in said target object according to said category comprises: determining the target object as the dynamic target in response to the type of the target object being a set type.
In one embodiment, the first laser point cloud is a frame in an image sequence that further includes a second laser point cloud acquired before the first laser point cloud; said determining said dynamic target in said target object according to said category comprises:
determining the target object as an object to be selected in response to the type of the target object being a set type;
and tracking the determined dynamic target in the second laser point cloud in the object to be selected, and determining the object to be selected as the dynamic target under the condition that the tracked object to be selected is determined to be in a motion state.
In one embodiment, the setting categories include: people, vehicles, and flying objects.
In one embodiment, the positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud comprises:
and matching the static laser point cloud in the laser point cloud map, and positioning the scanning device according to a matching result.
In one embodiment, prior to said positioning the scanning device in a pre-acquired laser point cloud map from the static laser point cloud, the method further comprises:
acquiring multi-frame laser point cloud of a target area;
removing the point cloud of the dynamic target in the laser point cloud to obtain a preprocessed laser point cloud;
and performing interframe matching on multiple frames of the preprocessed laser point clouds to construct the laser point cloud map.
In a second aspect, embodiments of the present disclosure provide a laser point cloud positioning device. The device comprises:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring first laser point clouds through a scanning device, and the first laser point clouds comprise point clouds of a dynamic target and point clouds of a static target;
the removing module is used for removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud; and
and the positioning module is used for positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
In one embodiment, the removal module comprises:
the identification unit is used for identifying the type of a target object in the first laser point cloud;
a determining unit, configured to determine the dynamic target in the target object according to the category; and
and the removing unit is used for removing the point cloud identifying the dynamic target to obtain the static laser point cloud.
In an embodiment, the determining unit is specifically configured to determine the target object as the dynamic target in response to the type of the target object being a set type.
In one embodiment, the first laser point cloud is a frame in an image sequence that further includes a second laser point cloud acquired before the first laser point cloud; the determination unit includes:
the first determining subunit is used for determining the target object as an object to be selected in response to the fact that the type of the target object is a set type; and
and the second determining subunit is used for identifying the object to be selected in the motion state in the first laser point cloud according to the second laser point cloud, and determining the object to be selected in the motion state as the dynamic target.
In one embodiment, the positioning module is specifically configured to match the static laser point cloud in the laser point cloud map and position the scanning device according to the matching result.
In one embodiment, the apparatus further comprises:
the acquisition module is used for acquiring multi-frame laser point clouds of a target area;
the removing module is used for removing the point cloud of the dynamic target in the laser point cloud to obtain a preprocessed laser point cloud; and
and the matching module is used for performing interframe matching on the preprocessed laser point cloud to construct the laser point cloud map.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
a memory storing executable instructions; and
and the processor executes the executable instructions stored in the memory to realize the steps of the laser point cloud positioning method provided by the first aspect.
In a fourth aspect, an embodiment of the present disclosure provides a laser point cloud positioning system, including:
a movement device which is used for moving the robot,
the laser radar is fixedly arranged on the moving device and used for acquiring first laser point cloud;
and, the electronic device provided by the third aspect.
The laser point cloud positioning method, the laser point cloud positioning device, the electronic equipment and the laser point cloud positioning system provided by the disclosure have the following beneficial effects:
according to the laser point cloud positioning method provided by the embodiment of the disclosure, the dynamic target point cloud in the laser point cloud is removed, the interference of the weak dynamic target point cloud on the positioning effect is eliminated, the accuracy of the positioning effect is improved, and the positioning calculation amount is reduced. The positioning method can quickly and accurately feed back the current position of the user scanning device in an application scene, and optimizes user experience.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a schematic flow diagram illustrating a laser point cloud localization method according to an exemplary embodiment;
FIG. 2 is a schematic flow diagram illustrating a laser point cloud localization method according to another exemplary embodiment;
FIG. 3 is a schematic flow diagram illustrating a laser point cloud localization method according to another exemplary embodiment;
FIG. 4 is a schematic flow diagram illustrating a laser point cloud localization method according to another exemplary embodiment;
FIG. 5 is a block diagram of a laser point cloud locating device shown in accordance with an exemplary embodiment;
FIG. 6 is a block diagram of an electronic device shown in accordance with an example embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of the terms "a" or "an" and the like in the description and in the claims of this disclosure do not denote a limitation of quantity, but rather denote the presence of at least one. Unless otherwise indicated, the word "comprise" or "comprises", and the like, means that the element or item listed before "comprises" or "comprising" covers the element or item listed after "comprises" or "comprising" and its equivalents, and does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
As used in the specification and claims of this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
In the laser point cloud positioning method provided in the related art, the laser point cloud collected by the scanning device is matched with a pre-acquired laser point cloud map to obtain the positioning of the scanning device. However, the laser point clouds collected by the scanning device include laser electric clouds of dynamic targets (such as pedestrians and vehicles), and the laser point clouds of the dynamic targets interfere with the map matching process of the laser point clouds and the laser point clouds, so that the matching precision and speed are reduced, and the positioning precision and positioning efficiency of the scanning device are affected.
Based on the above problems, the embodiments of the present disclosure provide a laser point cloud positioning method, device, electronic device, and system.
Fig. 1 is a schematic flow diagram illustrating a laser point cloud localization method according to an exemplary embodiment. As shown in fig. 1, the method includes:
step 101, acquiring a first laser point cloud through a scanning device. Optionally, the scanning device acquires a laser point cloud sequence, and the first laser point cloud is one frame in the image sequence. The scanning device can be selected as a laser radar, and outputs the first laser point cloud by outputting laser according to the received laser reflected by the external object.
The first laser point cloud includes a point cloud of a dynamic target and a point cloud of a static target. Target objects include, among others, dynamic objects (e.g., pedestrians, vehicles, flying objects, etc.) and static objects (e.g., buildings, plants, traffic safety facilities, etc.).
And 102, removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud.
By adopting the mode, the static laser point cloud only comprises the point cloud of the static target, and then in the subsequent positioning process, the static laser point cloud of the dynamic target point cloud is removed as the positioning basis, so that the interference of the dynamic target point cloud to the positioning process is weakened.
FIG. 2 is a flowchart illustrating step 102, according to an example embodiment. In one example, as shown in FIG. 2, step 102 comprises:
and 1021, identifying the type of the target object in the first laser point cloud.
Optionally, a pre-trained laser point cloud recognition model is adopted to extract feature information of the target object in the first laser point cloud, and then the type of the target object is recognized according to the feature information. Wherein the identifiable categories include, but are not limited to: people, vehicles, buildings, plants, traffic safety facilities.
Step 1022, determining the dynamic target in the target object according to the category.
In this example, two different dynamic targeting approaches are provided, as set forth in sub-cases below.
As a first optional manner, step 1022 specifically includes: and determining the target object as the dynamic target in response to the type of the target object being the set type.
Illustratively, the category is set to a category of a target object having a moving capability, such as a person, a vehicle, or the like. In such a case, the target having the moving capability is regarded as the dynamic target regardless of whether the target object is displaced or not. Accordingly, the static laser point cloud obtained in step 102 only includes point clouds of target objects (such as buildings, plants, traffic installation settings, etc.) without moving capability, further weakening the interference of dynamic targets on the subsequent positioning process.
As a second alternative, the first laser point cloud is a frame in the image sequence. At this time, the scanning device acquires a set of image sequences that further includes a second laser point cloud acquired before the first laser point cloud is acquired. In such a case, FIG. 3 is a flowchart illustrating step 1022 according to an exemplary embodiment. As shown in fig. 3, step 1022 specifically includes:
step 1022a, in response to the type of the target object being the set type, determining the target object as the candidate object.
Illustratively, the setting category includes a category of a target object having a moving capability, such as a person, a vehicle, and the like. For example, the vehicle identified in the first laser point cloud may be a vehicle in motion or a vehicle parked at the roadside. Obviously, a vehicle parked on the roadside is in a stationary state. At this time, the target object of the set type is used as a candidate object for subsequent screening.
And 1022b, tracking the determined dynamic target in the second laser point cloud in the object to be selected of the first laser point cloud, and determining the object to be selected as the dynamic target under the condition that the tracked object to be selected is determined to be in a motion state.
Since the first laser point cloud and the second laser point cloud are adjacently acquired, the first laser point cloud and the second laser point cloud include laser point clouds of the same object. Based on this, the actually moving object can be identified in the candidate objects determined in step 1022a through step 1022 b. In this way, the dynamic target recognition accuracy is optimized by two recognition (candidate recognition and dynamic target recognition).
Optionally, when determining whether the tracked object to be selected is in a motion state, for one object to be selected, the position of the object to be selected is represented by the central position of the laser point cloud of the object to be selected. And then, judging whether the object to be selected has displacement according to the position of the object to be selected in the first laser point cloud and the position of the same object in the second laser point cloud. And under the condition of judging that the object to be selected has displacement, determining that the object to be selected is in a motion state.
In a second optional mode, the target objects are preliminarily screened according to the types of the target objects to obtain objects to be selected, and then the objects in motion states in the objects to be selected are determined as dynamic objects, so that the identification accuracy of the dynamic objects is optimized.
In addition, more target objects used for positioning reference are reserved in the static laser point cloud obtained based on the method, and the matching precision and the matching efficiency of the static laser point cloud in the laser point cloud map are improved on the premise of reducing the dynamic target interference. For example, in a closed scene such as an underground garage, the similarity of different static targets (such as buildings) is high and the arrangement is repeated, and at this time, the difficulty in positioning by using a static laser point cloud only including the static targets is high. However, the static laser point cloud acquired in the second alternative includes a non-driving vehicle. That is, the dynamic target not in motion is also used as the target object of the positioning reference, thereby optimizing the positioning efficiency and the positioning accuracy.
With continued reference to fig. 2, step 1023 is performed after step 1022, as follows:
and 1023, removing the point cloud of the identified dynamic target to obtain the static laser point cloud.
Through steps 1021 to 1023, static laser point cloud with dynamic target interference removed is obtained. The static laser point cloud only comprises the point cloud of the static target, so that the interference of the point cloud of the dynamic target on the static laser point cloud is weakened, and the positioning precision and the positioning efficiency of positioning the static laser point cloud in the pre-obtained laser point cloud map are improved.
With continued reference to fig. 1, after step 102, step 103 is executed, specifically:
and 103, positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
Illustratively, the static laser point cloud is matched in the laser point cloud map through Normal Distribution Transform (NDT), and a matching result is obtained. The matching result represents the position of the static laser point cloud in the coordinate system of the laser point cloud map, so that the scanning device can be positioned in the laser point cloud map according to the matching result.
According to the laser point cloud positioning method provided by the embodiment of the disclosure, the accuracy of the positioning effect is improved and the positioning calculation amount is reduced by removing the dynamic target point cloud in the laser point cloud. The current position of the scanning device can be fed back to the user more quickly and accurately in an application scene, and the user experience is optimized.
In one embodiment, before step 101, the laser point cloud positioning method further comprises a step of laser point cloud map construction to obtain a laser point cloud map for matching with the static laser point cloud. FIG. 4 is a laser point cloud localization method shown in accordance with another exemplary embodiment. As shown in fig. 4, before step 101, the laser point cloud positioning method further includes:
step 401, obtaining multi-frame laser point clouds of a target area. The scanning device obtains multiple frames of laser point clouds according to a set time interval or a set distance interval in the moving process.
And 402, removing the point cloud of the dynamic target in the laser point cloud to obtain the preprocessed laser point cloud.
And 403, performing interframe matching on the multi-frame preprocessed laser point cloud to construct a laser point cloud map. Illustratively, an NDT algorithm is adopted to perform inter-frame matching on multi-frame preprocessed laser point clouds, coordinates of adjacent frame laser point clouds are unified, and then a laser point cloud map is constructed.
Wherein, the dynamic target in step 402 can be selected as a target object with moving capability or a target object in motion state. Optionally, the dynamic object verification method in step 402 is the same as the dynamic object verification method employed in step 1022 described above.
Taking the example of determining the target object with the movement capability as the dynamic object in step 1022, in this case, the target object with the movement capability is also determined as the dynamic object in step 402. In this manner, the laser point cloud map constructed in step 403 does not contain a point cloud of target objects with movement capabilities. The static laser point cloud obtained in step 102 also does not contain a point cloud of a target object with movement capability. Therefore, the static laser point cloud is positioned based on the laser point cloud map, so that the matching precision can be further improved, and the calculation amount can be reduced.
Dynamic objects are not displayed in the laser point cloud map constructed in the steps 401 to 403. The laser point cloud map is adopted for positioning, so that the interference of dynamic target point clouds is further weakened, the positioning accuracy is optimized, and the positioning calculation amount is reduced.
Based on the laser point cloud positioning method, the embodiment of the disclosure also provides a laser point cloud positioning device. FIG. 5 is a block diagram of a laser point cloud locating device output in accordance with an exemplary embodiment. As shown in fig. 5, the laser point cloud positioning apparatus 500 includes: an acquisition module 510, a removal module 520, and a positioning module 530.
The obtaining module 510 is configured to obtain a first laser point cloud through a scanning device.
The removing module 520 is configured to remove a point cloud of the dynamic target from the first laser point cloud to obtain a static laser point cloud.
The positioning module 530 is configured to position the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
In one embodiment, the removal module comprises: the device comprises an identification unit, a determination unit and a removal unit.
The identification unit is used for identifying the type of the target object in the first laser point cloud.
The determining unit is used for determining the dynamic target in the target object according to the category.
The removing unit is used for removing the point cloud for identifying the dynamic target to obtain the static laser point cloud.
In an embodiment, the determining unit is specifically configured to determine the target object as the dynamic target in response to the category of the target object being the set category.
In one embodiment, the first laser point cloud is a frame in an image sequence, the image sequence further comprising a second laser point cloud acquired before the first laser point cloud; the determination unit includes: a first determining subunit and a second determining subunit.
The first determining subunit is configured to determine, in response to that the type of the target object is the set type, the target object as the object to be selected.
The second determining subunit is configured to track the determined dynamic target in the second laser point cloud in the object to be selected in the first laser point cloud, and determine the object to be selected as the dynamic target when it is determined that the tracked object to be selected is in a moving state.
In one embodiment, the positioning module is specifically configured to match a static laser point cloud in a laser point cloud map and position the scanning device according to the matching result.
In one embodiment, the apparatus further comprises: the device comprises an acquisition module, a removal module and a matching module.
The acquisition module is used for acquiring multi-frame laser point clouds in a target area.
The removing module is used for removing the point cloud of the dynamic target in the laser point cloud to obtain the preprocessed laser point cloud.
And the matching module is used for performing interframe matching on the preprocessed laser point cloud to construct a laser point cloud map.
The embodiment of the disclosure also provides an electronic device. FIG. 6 is a block diagram of an electronic device shown in accordance with an example embodiment. As illustrated in fig. 6, the electronic device includes: a memory and a processor.
The memory has stored thereon executable instructions. The processor is used for executing executable instructions stored in the memory to realize the steps of the laser point cloud positioning method provided above.
Furthermore, embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements a method as in any one of the above.
The embodiment of the disclosure also provides a laser point cloud positioning system. The laser point cloud positioning system comprises: a moving device (e.g., a vehicle), a lidar fixedly mounted on the moving device, and the electronics provided above. The laser radar is used for acquiring laser point cloud of a target area, and the electronic equipment realizes the positioning of the movement device based on the laser point cloud acquired by the laser radar.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Computers suitable for executing computer programs include, for example, general and/or special purpose microprocessors, or any other type of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer does not necessarily have such a device. Moreover, a computer may be embedded in another device, e.g., a mobile telephone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., an internal hard disk or a removable disk), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. In other instances, features described in connection with one embodiment may be implemented as discrete components or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Further, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice in the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims (10)

1. A laser point cloud localization method, the method comprising:
acquiring a first laser point cloud through a scanning device;
removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud;
and positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
2. The method of claim 1, wherein removing the point cloud of the dynamic target from the first laser point cloud results in a static laser point cloud, comprising:
identifying a category of a target object in the first laser point cloud;
determining the dynamic target in the target object according to the category;
and removing the point cloud identifying the dynamic target to obtain the static laser point cloud.
3. The method of claim 2, wherein said determining the dynamic target in the target object according to the category comprises:
determining the target object as the dynamic target in response to the type of the target object being a set type.
4. The method of claim 2, wherein the first laser point cloud is a frame in a sequence of images further comprising a second laser point cloud acquired before the first laser point cloud; said determining said dynamic target in said target object according to said category comprises:
determining the target object as an object to be selected in response to the type of the target object being a set type;
and tracking the determined dynamic target in the second laser point cloud in the object to be selected, and determining the object to be selected as the dynamic target under the condition that the tracked object to be selected is determined to be in a motion state.
5. The method according to any one of claims 3 or 4, wherein the setting category comprises: people, vehicles, and flying objects.
6. The method of claim 1, wherein said positioning the scanning device in a pre-acquired map of laser point clouds from the static laser point clouds comprises:
and matching the static laser point cloud in the laser point cloud map, and positioning the scanning device according to a matching result.
7. The method of claim 1, wherein prior to said positioning the scanning device in a pre-acquired map of laser point clouds from the static laser point clouds, the method further comprises:
acquiring multi-frame laser point cloud of a target area;
removing the point cloud of the dynamic target in the laser point cloud to obtain a preprocessed laser point cloud;
and performing interframe matching on multiple frames of the preprocessed laser point clouds to construct the laser point cloud map.
8. A laser point cloud positioning apparatus, the apparatus comprising:
the acquisition module is used for acquiring a first laser point cloud through a scanning device;
the removing module is used for removing the point cloud of the dynamic target in the first laser point cloud to obtain a static laser point cloud; and
and the positioning module is used for positioning the scanning device in a pre-acquired laser point cloud map according to the static laser point cloud.
9. An electronic device, characterized in that the electronic device comprises:
a memory storing executable instructions; and
a processor executing executable instructions stored in the memory to implement the steps of the method of any of claims 1-7.
10. A laser point cloud positioning system, the system comprising:
a movement device which is used for moving the robot,
the laser radar is fixedly arranged on the moving device and used for acquiring first laser point cloud;
and, the electronic device of claim 9.
CN202010469927.5A 2020-05-28 2020-05-28 Laser point cloud positioning method, device, equipment and system Pending CN111551947A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010469927.5A CN111551947A (en) 2020-05-28 2020-05-28 Laser point cloud positioning method, device, equipment and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010469927.5A CN111551947A (en) 2020-05-28 2020-05-28 Laser point cloud positioning method, device, equipment and system

Publications (1)

Publication Number Publication Date
CN111551947A true CN111551947A (en) 2020-08-18

Family

ID=71998904

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010469927.5A Pending CN111551947A (en) 2020-05-28 2020-05-28 Laser point cloud positioning method, device, equipment and system

Country Status (1)

Country Link
CN (1) CN111551947A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112180343A (en) * 2020-09-30 2021-01-05 东软睿驰汽车技术（沈阳）有限公司 Laser point cloud data processing method, device and equipment and unmanned system
CN112200868A (en) * 2020-09-30 2021-01-08 深兰人工智能(深圳)有限公司 Positioning method, device and vehicle
CN115014369A (en) * 2022-05-20 2022-09-06 苏州艾吉威机器人有限公司 Method and device for filtering dynamic objects from laser point cloud
CN116546424A (en) * 2023-02-07 2023-08-04 智道网联科技(北京)有限公司 Laser mapping method and device, laser positioning method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170124781A1 (en) * 2015-11-04 2017-05-04 Zoox, Inc. Calibration for autonomous vehicle operation
US20190011566A1 (en) * 2017-07-04 2019-01-10 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for identifying laser point cloud data of autonomous vehicle
CN109285220A (en) * 2018-08-30 2019-01-29 百度在线网络技术（北京）有限公司 A kind of generation method, device, equipment and the storage medium of three-dimensional scenic map
CN110533055A (en) * 2018-05-25 2019-12-03 北京京东尚科信息技术有限公司 A method and device for processing point cloud data
CN110795523A (en) * 2020-01-06 2020-02-14 中智行科技有限公司 Vehicle positioning method and device and intelligent vehicle

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170124781A1 (en) * 2015-11-04 2017-05-04 Zoox, Inc. Calibration for autonomous vehicle operation
US20190011566A1 (en) * 2017-07-04 2019-01-10 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for identifying laser point cloud data of autonomous vehicle
CN110533055A (en) * 2018-05-25 2019-12-03 北京京东尚科信息技术有限公司 A method and device for processing point cloud data
CN109285220A (en) * 2018-08-30 2019-01-29 百度在线网络技术（北京）有限公司 A kind of generation method, device, equipment and the storage medium of three-dimensional scenic map
CN110795523A (en) * 2020-01-06 2020-02-14 中智行科技有限公司 Vehicle positioning method and device and intelligent vehicle

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112180343A (en) * 2020-09-30 2021-01-05 东软睿驰汽车技术（沈阳）有限公司 Laser point cloud data processing method, device and equipment and unmanned system
CN112200868A (en) * 2020-09-30 2021-01-08 深兰人工智能(深圳)有限公司 Positioning method, device and vehicle
CN115014369A (en) * 2022-05-20 2022-09-06 苏州艾吉威机器人有限公司 Method and device for filtering dynamic objects from laser point cloud
CN115014369B (en) * 2022-05-20 2025-07-25 苏州艾吉威机器人有限公司 Method and device for filtering dynamic object by laser point cloud
CN116546424A (en) * 2023-02-07 2023-08-04 智道网联科技(北京)有限公司 Laser mapping method and device, laser positioning method and device

Similar Documents

Publication Publication Date Title
US11105639B2 (en) Map refinement using feature extraction from images
EP3881226B1 (en) Object classification using extra-regional context
CN111551947A (en) Laser point cloud positioning method, device, equipment and system
CN110147706B (en) Obstacle recognition method and device, storage medium, and electronic device
Datondji et al. A survey of vision-based traffic monitoring of road intersections
US20240112292A1 (en) Vehicle terminal device, service server, method, computer program, computer readable recording medium for providing driving related guidance service
Chan et al. Vehicle detection and tracking under various lighting conditions using a particle filter
US10949712B2 (en) Information processing method and information processing device
US10643472B2 (en) Monitor apparatus and monitor system
US11956693B2 (en) Apparatus and method for providing location
CN111942379A (en) Vehicle control device and vehicle control method
CN113112524B (en) Track prediction method and device for moving object in automatic driving and computing equipment
KR102517086B1 (en) Apparatus and method for generating a lane polyline using a neural network model
CN113256731A (en) Target detection method and device based on monocular vision
US20210174113A1 (en) Method for limiting object detection area in a mobile system equipped with a rotation sensor or a position sensor with an image sensor, and apparatus for performing the same
Kumar et al. Indoor localization of vehicles using deep learning
Dahal et al. An online learning system for wireless charging alignment using surround-view fisheye cameras
WO2018052714A2 (en) Video to radar
Kang et al. Map building based on sensor fusion for autonomous vehicle
Ess et al. Improved multi-person tracking with active occlusion handling
CN114820699A (en) Multi-target tracking method, device, equipment and medium
Kim et al. Data fusion in 3D vision using a RGB-D data via switching observation model and its application to people tracking
CN115342811A (en) Path planning method, device, equipment and storage medium
CN117804423A (en) A relocation method and device
Christian et al. Radar and camera fusion for object forecasting in driving scenarios

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200818